Summary of Dsti at Llms4ol 2024 Task A: Intrinsic Versus Extrinsic Knowledge For Type Classification, by Hanna Abi Akl
DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification
by Hanna Abi Akl
First submitted to arxiv on: 26 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a new method called “semantic towers” that represents knowledge outside of large language models, contrasting it with knowledge internal to these models for ontology learning. The research investigates the performance and semantic grounding trade-offs between extrinsic and intrinsic knowledge in large language models. The results are benchmarked on the Large Language Models for Ontology Learning (LLMs4OL) 2024 challenge. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers developed a new way of representing knowledge, called “semantic towers,” that exists outside of language models. They compared this to how language models represent information internally and found that there’s a trade-off between how well something performs and how well it understands what it means. This is important for learning about relationships between things. |
Keywords
* Artificial intelligence * Grounding
